Run predictions from state-of-the-art machine learning models right from your browser. Use intuitive GUIs, no preprocessing or coding required! You can upload your own models here by logging into your Gradio account with GitHub and uploading a GitHub repository.
GANs N' Roses: Stable, Controllable, Diverse Image to Image Translation (works for videos too!)
Anime2Sketch: A Sketch Extractor for Anime Arts with Deep Networks
Towards Real-time and Light-weight Line Segment Detection
GPT-Neo: Large Scale Autoregressive Language Modeling with Mesh-Tensorflow
Is a Green Screen Really Necessary for Real-Time Portrait Matting?
neural waveshaping synthesis
neural waveshaping synthesis: real-time neural audio synthesis in the waveform domain
Towards Fast, Accurate and Stable 3D Dense Face Alignment
Real-time Facial Surface Geometry from Monocular Video on Mobile GPUs
demo for piano transcription
demo for DialoGPT
demo for SimCSE
demo for OpenAI CLIP: Connecting Text and Images for visual classification
DeepLab2: A TensorFlow Library for Deep Labeling
demo for ctrlsum
A super resolution model. Try it with your low resolution images now!
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
demo for yolov5
Demo for GPT-neo and m2m using Gradio Series
Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech
Predict a sketch
A Convolution Neural Network model trained on Google's QuickDraw dataset.
multilingual text2image search for 50+ languages using Sentence Transformers and CLIP
Pop Music Transformer
Pop Music Transformer: Beat-based Modeling and Generation of Expressive Pop Piano Compositions
demo for Image Classification using VIT and Deit with gradio parallel
Instagram Filter Removal with PyTorch
Demo for Instagram Filter Removal on Fashionable Images with PyTorch
demo for MobileStyleGAN
Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speech
demo for layout-parser
Longformer: The Long-Document Transformer
demo for m2m100
HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units
demo for speech seperation using speechbrain
demo for GPT-2
NUBIA stands for 'NeUral Based Interchangeability Assessor'. NUBIA gives a score on a scale of 0 to 1 reflecting how much it thinks the candidate text is interchangeable with the reference text.
A simple pdf to audio converter.
demo for wav2vec 2.0
Identifying Skin Cancer
Predicts whether an image of skin is cancerous or not. This model is EXPERIMENTAL and should only be used for research purposes.
Emerging Properties in Self-Supervised Vision Transformers
xlm-t demo for multilingual sentiment classification
ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators
nussl (pronounced 'nuzzle') is a flexible, object oriented Python audio source separation library created by the Interactive Audio Lab at Northwestern University
ByT5-base fine-tuned for Question Answering
ByT5: Towards a token-free future with pre-trained byte-to-byte models
demo for deit
Upload a picture of a dino toy and learn which dinosaur it is
COVID-19 Pneumonia Detection from X-Rays
A model that can lighten the load for radiologists in trying to detect COVID-19 pneumonia from chest X-Rays. The model was able to achieve a 90% F1-Score on unseen data.